fastfind.c revision 18905
1/* 2 * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin. 3 * Copyright (c) 1989, 1993 4 * The Regents of the University of California. All rights reserved. 5 * 6 * This code is derived from software contributed to Berkeley by 7 * James A. Woods. 8 * 9 * Redistribution and use in source and binary forms, with or without 10 * modification, are permitted provided that the following conditions 11 * are met: 12 * 1. Redistributions of source code must retain the above copyright 13 * notice, this list of conditions and the following disclaimer. 14 * 2. Redistributions in binary form must reproduce the above copyright 15 * notice, this list of conditions and the following disclaimer in the 16 * documentation and/or other materials provided with the distribution. 17 * 3. All advertising materials mentioning features or use of this software 18 * must display the following acknowledgement: 19 * This product includes software developed by the University of 20 * California, Berkeley and its contributors. 21 * 4. Neither the name of the University nor the names of its contributors 22 * may be used to endorse or promote products derived from this software 23 * without specific prior written permission. 24 * 25 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 26 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 27 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 28 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 29 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 30 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 31 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 32 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 33 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 34 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 35 * SUCH DAMAGE. 36 * 37 * $Id: fastfind.c,v 1.2 1996/10/09 00:33:32 wosch Exp $ 38 */ 39 40 41#ifndef _LOCATE_STATISTIC_ 42#define _LOCATE_STATISTIC_ 43 44void 45statistic (fp, path_fcodes) 46 FILE *fp; /* open database */ 47 char *path_fcodes; /* for error message */ 48{ 49 register int lines, chars, size, big, zwerg; 50 register u_char *p, *s; 51 register int c; 52 int count, umlaut; 53 u_char bigram1[NBG], bigram2[NBG], path[MAXPATHLEN]; 54 55 for (c = 0, p = bigram1, s = bigram2; c < NBG; c++) { 56 p[c] = check_bigram_char(getc(fp)); 57 s[c] = check_bigram_char(getc(fp)); 58 } 59 60 lines = chars = big = zwerg = umlaut = 0; 61 size = NBG + NBG; 62 63 for (c = getc(fp), count = 0; c != EOF; size++) { 64 if (c == SWITCH) { 65 count += getwf(fp) - OFFSET; 66 size += sizeof(int); 67 zwerg++; 68 } else 69 count += c - OFFSET; 70 71 for (p = path + count; (c = getc(fp)) > SWITCH; size++) 72 if (c < PARITY) { 73 if (c == UMLAUT) { 74 c = getc(fp); 75 size++; 76 umlaut++; 77 } 78 p++; 79 } else { 80 /* bigram char */ 81 big++; 82 p += 2; 83 } 84 85 p++; 86 lines++; 87 chars += (p - path); 88 } 89 90 (void)printf("\nDatabase: %s\n", path_fcodes); 91 (void)printf("Compression: Front: %2.2f%%, ", 92 (float)(100 * (size + big - (2 * NBG))) / chars); 93 (void)printf("Bigram: %2.2f%%, ", (float)(100 * (size - big)) / size); 94 (void)printf("Total: %2.2f%%\n", 95 (float)(100 * (size - (2 * NBG))) / chars); 96 (void)printf("Filenames: %d, ", lines); 97 (void)printf("Characters: %d, ", chars); 98 (void)printf("Database size: %d\n", size); 99 (void)printf("Bigram characters: %d, ", big); 100 (void)printf("Integers: %d, ", zwerg); 101 (void)printf("8-Bit characters: %d\n", umlaut); 102 103} 104#endif /* _LOCATE_STATISTIC_ */ 105 106 107void 108#ifdef FF_MMAP 109 110 111#ifdef FF_ICASE 112fastfind_mmap_icase 113#else 114fastfind_mmap 115#endif /* FF_ICASE */ 116(pathpart, paddr, len, database) 117 char *pathpart; /* search string */ 118 caddr_t paddr; /* mmap pointer */ 119 int len; /* length of database */ 120 char *database; /* for error message */ 121 122 123#else /* MMAP */ 124 125 126#ifdef FF_ICASE 127fastfind_icase 128#else 129fastfind 130#endif /* FF_ICASE */ 131 132(fp, pathpart, database) 133 FILE *fp; /* open database */ 134 char *pathpart; /* search string */ 135 char *database; /* for error message */ 136 137 138#endif /* MMAP */ 139 140{ 141 register u_char *p, *s, *patend, *q, *foundchar; 142 register int c, cc; 143 int count, found, globflag; 144 u_char *cutoff; 145 u_char bigram1[NBG], bigram2[NBG], path[MAXPATHLEN]; 146 147#ifdef FF_ICASE 148 /* use a lookup table for case insensitive search */ 149 u_char table[UCHAR_MAX + 1]; 150 151 tolower_word(pathpart); 152#endif /* FF_ICASE*/ 153 154 /* init bigram table */ 155#ifdef FF_MMAP 156 if (len < (2*NBG)) { 157 (void)fprintf(stderr, "database to small: %s\n", database); 158 exit(1); 159 } 160 161 for (c = 0, p = bigram1, s = bigram2; c < NBG; c++, len-= 2) { 162 p[c] = check_bigram_char(*paddr++); 163 s[c] = check_bigram_char(*paddr++); 164 } 165#else 166 for (c = 0, p = bigram1, s = bigram2; c < NBG; c++) { 167 p[c] = check_bigram_char(getc(fp)); 168 s[c] = check_bigram_char(getc(fp)); 169 } 170#endif /* FF_MMAP */ 171 172 /* find optimal (last) char for searching */ 173 for (p = pathpart; *p != '\0'; p++) 174 if (index(LOCATE_REG, *p) != NULL) 175 break; 176 177 if (*p == '\0') 178 globflag = 0; 179 else 180 globflag = 1; 181 182 p = pathpart; 183 patend = patprep(p); 184 cc = *patend; 185 186#ifdef FF_ICASE 187 /* set patend char to true */ 188 table[TOLOWER(*patend)] = 1; 189 table[toupper(*patend)] = 1; 190#endif /* FF_ICASE */ 191 192 193 /* main loop */ 194 found = count = 0; 195 foundchar = 0; 196 197#ifdef FF_MMAP 198 c = (u_char)*paddr++; len--; 199 for (; len > 0; ) { 200#else 201 c = getc(fp); 202 for (; c != EOF; ) { 203#endif /* FF_MMAP */ 204 205 /* go forward or backward */ 206 if (c == SWITCH) { /* big step, an integer */ 207#ifdef FF_MMAP 208 count += getwm(paddr) - OFFSET; 209 len -= INTSIZE; paddr += INTSIZE; 210#else 211 count += getwf(fp) - OFFSET; 212#endif /* FF_MMAP */ 213 } else { /* slow step, =< 14 chars */ 214 count += c - OFFSET; 215 } 216 217 /* overlay old path */ 218 p = path + count; 219 foundchar = p - 1; 220 221 for (;;) { 222#ifdef FF_MMAP 223 c = (u_char)*paddr++; 224 len--; 225#else 226 c = getc(fp); 227#endif /* FF_MMAP */ 228 /* 229 * == UMLAUT: 8 bit char followed 230 * <= SWITCH: offset 231 * >= PARITY: bigram 232 * rest: single ascii char 233 * 234 * offset < SWITCH < UMLAUT < ascii < PARITY < bigram 235 */ 236 if (c < PARITY) { 237 if (c <= UMLAUT) { 238 if (c == UMLAUT) { 239#ifdef FF_MMAP 240 c = (u_char)*paddr++; 241 len--; 242#else 243 c = getc(fp); 244#endif /* FF_MMAP */ 245 246 } else 247 break; /* SWITCH */ 248 } 249#ifdef FF_ICASE 250 if (table[c]) 251#else 252 if (c == cc) 253#endif /* FF_ICASE */ 254 foundchar = p; 255 *p++ = c; 256 } 257 else { 258 /* bigrams are parity-marked */ 259 TO7BIT(c); 260 261#ifndef FF_ICASE 262 if (bigram1[c] == cc || 263 bigram2[c] == cc) 264#else 265 266 if (table[bigram1[c]] || 267 table[bigram2[c]]) 268#endif /* FF_ICASE */ 269 foundchar = p + 1; 270 271 *p++ = bigram1[c]; 272 *p++ = bigram2[c]; 273 } 274 } 275 276 if (found) { /* previous line matched */ 277 cutoff = path; 278 *p-- = '\0'; 279 foundchar = p; 280 } else if (foundchar >= path + count) { /* a char matched */ 281 *p-- = '\0'; 282 cutoff = path + count; 283 } else /* nothing to do */ 284 continue; 285 286 found = 0; 287 for (s = foundchar; s >= cutoff; s--) { 288 if (*s == cc 289#ifdef FF_ICASE 290 || TOLOWER(*s) == cc 291#endif /* FF_ICASE */ 292 ) { /* fast first char check */ 293 for (p = patend - 1, q = s - 1; *p != '\0'; 294 p--, q--) 295 if (*q != *p 296#ifdef FF_ICASE 297 && TOLOWER(*q) != *p 298#endif /* FF_ICASE */ 299 ) 300 break; 301 if (*p == '\0') { /* fast match success */ 302 found = 1; 303 if (!globflag || !fnmatch(pathpart, path, 0)) { 304 if (f_silent) 305 counter++; 306 else if (f_limit) { 307 counter++; 308 if (f_limit >= counter) 309 (void)puts(path); 310 else { 311 (void)fprintf(stderr, "[show only %d lines]\n", counter - 1); 312 exit(0); 313 } 314 } else 315 (void)puts(path); 316 } 317 break; 318 } 319 } 320 } 321 } 322} 323